Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19685
    Prev
    Next
    INDEX
    Explanations

    names of locations and people

    oai_token-act-pair · gpt-3.5-turbo

    specific place names or geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reason
    -0.75
    catentry
    -0.67
    idas
    -0.64
    rez
    -0.64
    asy
    -0.63
     Qi
    -0.61
    Si
    -0.59
     OnePlus
    -0.57
    spec
    -0.55
    bug
    -0.55
    POSITIVE LOGITS
     Airport
    0.94
     Pradesh
    0.94
     itself
    0.90
     AFB
    0.87
     Town
    0.86
     City
    0.86
     guiActiveUn
    0.85
     Ferry
    0.82
     Borough
    0.82
     airport
    0.80
    Activations Density 0.219%

    No Known Activations